REA
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Turn the user's description or uploaded reference into a finished, editable Blender card and an interactive Three.js page. Preserve the requested subject, style, typography and destination. This skill contains code and text only; generated artwork belongs in the user's output project.
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/skills/everettfish-holo-card-studio)在同一工作中把 AI 连到服务的 MCP
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
MCP server for terminal commands, file operations, and process management
同类工作,排序与 Skill 列表相同
| 本项 holo-card-studio | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| 作者 | EverettFish | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skill 数 | 1 | 1 | 1 | 1 | 1 |
| GitHub 星标 | 2,111 | 467,235 | 234,125 | 149,873 | 144,332 |
| 最近代码更新 | 2026年9月22日 | 2026年11月18日 | 2026年4月20日 | 2026年11月18日 | 2026年11月18日 |
| 许可证 | – | MIT | – | Apache-2.0 | MIT |
EverettFish 提供的 1 个 Skill(指令集),AI 读取后照做 · 不是 MCP server
MCP = 手
把 AI 连到外部服务或数据,例如读取 Notion 或开发票。需要有程序或服务器在运行。
Skill = 手册
教 AI 怎么做某项工作的文本文件,不连接任何服务。
有些会重叠:少数 Skill 带有调用工具的脚本,少数 MCP 只提供知识。请从你想完成的工作出发。
Codex
依据开发者 README 和 repo 中的文件夹
GitHub account EverettFish (person), 1 years old
★ 2,111 stars · code last changed 2026年9月22日
36 scripts that can run on a computer: assets/web-holographic/app.js, assets/web-holographic/server.mjs, assets/web-lenticular/app.js, assets/web-lenticular/server.mjs and 32 more
Could not check every script (some are too large); read them first
No hooks or writes to machine settings found
Checked automatically from the repo files at commit cce9718 (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
第一步:你用哪个 AI?
选择你用的应用,本页只显示该应用的安装方法
This skill has no license, so we do not hand out a ZIP from our site. Download it from GitHub and arrange the folder yourself, or use "Let the AI install it" above, which is easier
Download from GitHub (whole repo) ↗
Unzip it, then zip only the holo-card-studio folder again. The ZIP must have a holo-card-studio folder with SKILL.md at the top level, no loose files
+Create skillUpload a skillpick holo-card-studio.zip
SettingsCapabilitiesCode execution and file creation
Turn on Code execution and file creation first (newer menus: Create and edit files) · personal plans: Settings → Capabilities · Team/Enterprise: an admin turns it on under Organization settings → Plugins & skills · every plan, including Free
Upload once; it works in claude.ai and Claude Desktop, and in recent Claude Code signed in with a Claude account (not with an API key)
Cowork and cloud sessions use the skills turned on in your claude.ai account, not ~/.claude/skills on your computer (Claude Desktop scheduled tasks run locally and still load it)
Checked against official docs 2026年11月12日 · Source: support.claude.com, support.claude.com, code.claude.com
复制这句话,粘贴到 Claude Code 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
重新打开 Claude Code,输入 /holo-card-studio,或直接提出相关任务,Claude 会自动选用
Checked against official docs 2026年11月12日 · Source: code.claude.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
git clone --depth 1 https://github.com/everettfish/holo-card-studio.git /tmp/popnx-skill-everettfish-holo-card-studio-cce9718 && mkdir -p ~/.claude/skills && cp -R '/tmp/popnx-skill-everettfish-holo-card-studio-cce9718/.' ~/.claude/skills/holo-card-studioChatGPT 桌面应用内置 Codex,Codex 从 ~/.agents/skills 文件夹读取 Skill
在 ChatGPT 桌面应用中打开 Codex,把这句话粘贴到对话中
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
把 holo-card-studio 文件夹放到 ~/.agents/skills/holo-card-studio
~ 是你的主文件夹($HOME)
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
git clone --depth 1 https://github.com/everettfish/holo-card-studio.git /tmp/popnx-skill-everettfish-holo-card-studio-cce9718 && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-everettfish-holo-card-studio-cce9718/.' ~/.agents/skills/holo-card-studioChecked against official docs 2026年11月15日 · Source: learn.chatgpt.com
不能使用你自己安装的 Skill,只能使用目录中插件自带的 Skill
想在 ChatGPT 中使用这个 Skill,请按上面的方法使用 ChatGPT 桌面应用
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
复制这句话,粘贴到 Codex 的对话中 · 适用于 ChatGPT 桌面应用中的 Codex、Codex CLI 和 IDE 扩展
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex 会自动发现新安装的 Skill;如果没有出现,请重启 Codex · 使用方法:在 ChatGPT 中输入 @ 并选择 Skill · 在 Codex CLI 或 IDE 扩展中运行 /skills,或输入 $ 加 Skill 名称
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
git clone --depth 1 https://github.com/everettfish/holo-card-studio.git /tmp/popnx-skill-everettfish-holo-card-studio-cce9718 && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-everettfish-holo-card-studio-cce9718/.' ~/.agents/skills/holo-card-studio复制这句话,粘贴到 Cursor 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
在 Cursor 的 Agent 聊天中输入 / 并选择 holo-card-studio
Checked against official docs 2026年11月12日 · Source: cursor.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
git clone --depth 1 https://github.com/everettfish/holo-card-studio.git /tmp/popnx-skill-everettfish-holo-card-studio-cce9718 && mkdir -p ~/.cursor/skills && cp -R '/tmp/popnx-skill-everettfish-holo-card-studio-cce9718/.' ~/.cursor/skills/holo-card-studio适用于其他能读取 Skill 的应用。这句话列出了 Claude Code、Codex 和 Cursor 的路径,AI 会按你的应用选择 · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs 2026年11月12日 · Source: code.claude.com, learn.chatgpt.com, cursor.com
其他支持 Agent Skills 的应用(如 Gemini CLI、GitHub Copilot)使用不同文件夹,请查看该应用的指南,再把含 SKILL.md 的文件夹复制过去。
已于 2026年11月11日 对照 Claude Code、Codex 和 Cursor 官方指南核实 skill 文件夹
✓ 命令已检查 2026年11月18日
以下文字来自开发者的 repo,不是 PopNx MCP 的指令
5,434 个字符 · 在 GitHub 打开完整文件
---
name: holo-card-studio
description: Create collectible holographic foil cards and two-image lenticular flip cards with AI-generated full-color ukiyo-e and colored sumi-e anime artwork, layered Blender scenes, renders, GLB export, and a flat white web viewer. Use for 镭射卡、闪卡、全息卡、光栅卡、一念神魔、双形态卡、角色收藏卡,或需要保持角色高度一致的 A/B 状态切换。
---
# Holo Card Studio
Create a finished collectible card project. The skill has two production routes that share one art direction and one delivery standard.
## Route first
Choose exactly one route before preparing assets:
- **Holographic foil** is the default route for one character artwork. It uses separate `subject`, `background`, `lineart`, and `text` planes, plus foil and sparkle effects.
- **Two-image lenticular** is the route for `光栅`, `翻转`, `双图`, `双形态`, or `一念神魔`. It uses two complete card artworks, A and B, and changes the whole card with viewing angle. Do not split one picture into left/right halves and do not fake the two states with SVG.
If the user asks for 一念神魔, route to lenticular automatically.
## Default art direction
Read [references/art-direction.md](references/art-direction.md) before generating art. Unless the user supplies another style, every generated card uses full-color Japanese ukiyo-e composition with colored sumi-e anime linework: expressive thick-to-thin ink contours, mineral pigments, visible brush texture, dramatic movement, and a coherent illustrated environment.
For a two-state card, generate A first, then edit A into B with the image-generation tool. Repeat the identity and composition invariants in the edit prompt. Keep the same face structure, hair/fur, costume anchors, proportions, camera, crop, body scale, and major silhouette. Expressions must clearly communicate the state: the benevolent state is serene, compassionate, and resolute; the malevolent state has focused predatory eyes, sharper brows, and a controlled feral or cruel expression without changing identity.
Foil and diamond sparkle are presentation layers, not substitutes for artwork. Default `foil` and `particles` to `1.0`; keep the face readable and preserve the ink contours.
## Generate images
Use the built-in image-generation tool for raster artwork. Do not ask the user to generate the images elsewhere. Do not use SVG or procedural stand-ins when a final illustration is requested.
For no-reference generation:
1. Generate the complete A artwork from the character brief using the default style.
2. Generate B by editing A. Lock identity, framing, and major geometry; change the expression, state-specific costume details, lighting, atmosphere, and action effects.
3. Save both as portrait PNG files with identical dimensions.
For reference-driven generation, treat the reference as the identity source and A as the direct adaptation. Then edit A into B. Read [references/lenticular-route.md](references/lenticular-route.md) for the required prompt structure and alignment checks.
## Build the project
Create a user-owned project directory outside this skill. Copy the matching example config and prepare its assets.
Holographic assets:
```text
assets/subject.png
assets/background.png
assets/lineart.png
assets/text.png
card-config.json
```
Lenticular assets:
```text
assets/image_a.png
assets/image_b.png
assets/text.png
card-config.json
```
Run the shared dispatcher:
```powershell
python scripts/run_pipeline.py --project <project-dir> --mode holographic
python scripts/run_pipeline.py --project <project-dir> --mode lenticular
```
`--mode` may be omitted when `card-config.json` contains `"mode"`. The default is `holographic`.
For lenticular projects, run `scripts/lenticular/prepare_pair.py` before the pipeline when normalization or an alignment report is needed. The pipeline creates typography when `text.png` is absent, validates assets, builds `card.blend`, renders previews, exports `web/assets/card.glb`, copies the matching web viewer, and installs its local web dependencies unless `--skip-npm` is supplied.
## Verify and deliver
Read [references/verification.md](references/verification.md). At minimum verify:
- the Blender scene contains physical card depth and multiple effect planes;
- A and B replace the entire illustrated face and remain recognizable as one character;
- front and angled renders show a readable state change;
- foil, glitter, line glow, and lenticular ridges are visible without washing out the face;
- the white web viewer loads the GLB and supports pointer/touch tilt without horizontal overflow.
Deliver the source images, `card.blend`, renders, web viewer, and a validation report. Keep generated binaries in the project, never inside the reusable skill archive.
## References
- [references/art-direction.md](references/art-direction.md): shared default style and prompt recipes.
- [references/holographic-route.md](references/holographic-route.md): multilayer foil-card workflow.
- [references/lenticular-route.md](references/lenticular-route.md): full-image A/B workflow and identity lock.
- [references/config.holographic.example.json](references/config.holographic.example.json): single-art config.
- [references/config.lenticular.example.json](references/config.lenticular.example.json): two-state config.
- [references/lenticular-model.md](references/lenticular-model.md): view-angle model.
- [references/verification.md](references/verification.md): render and browser acceptance checks.
提问、分享技巧或报告无法使用。按“有帮助”数量排序。